config.json

{
  "architectures": [
    "Qwen2AudioForConditionalGeneration"
  ],
  "audio_config": {
    "activation_dropout": 0.0,
    "activation_function": "gelu",
    "attention_dropout": 0.0,
    "d_model": 16,
    "dropout": 0.0,
    "encoder_attention_heads": 4,
    "encoder_ffn_dim": 32,
    "encoder_layerdrop": 0.0,
    "encoder_layers": 2,
    "initializer_range": 0.02,
    "max_source_positions": 1500,
    "model_type": "qwen2_audio_encoder",
    "num_hidden_layers": 2,
    "num_mel_bins": 128,
    "scale_embedding": false
  },
  "audio_token_index": 151646,
  "dtype": "bfloat16",
  "ignore_index": -100,
  "model_type": "qwen2_audio",
  "text_config": {
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "dtype": "bfloat16",
    "eos_token_id": 151645,
    "hidden_act": "silu",
    "hidden_size": 16,
    "initializer_range": 0.02,
    "intermediate_size": 32,
    "layer_types": [
      "full_attention",
      "full_attention"
    ],
    "max_position_embeddings": 8192,
    "max_window_layers": 28,
    "model_type": "qwen2",
    "num_attention_heads": 4,
    "num_hidden_layers": 2,
    "num_key_value_heads": 2,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 10000,
    "sliding_window": null,
    "use_cache": true,
    "use_mrope": false,
    "use_sliding_window": false,
    "vocab_size": 156032
  },
  "transformers_version": "4.56.2",
  "vocab_size": 156032
}